Speech Note NVIDIA

<ul>
 <li>whisper.cpp update to version 1.7.1</li>
 <li>PyTorch update to version 2.5.1</li>
 <li>cuDNN update to version 9.5.1</li>
 </ul>

<ul>
 <li>AVX2 and FMA are no longer required to run WhisperCpp when using GPU acceleration.</li>
 </ul>

<ul>
 <li>whisper.cpp update to version 1.6.2</li>
 <li>CTranslate2 update to version 4.3.1</li>
 </ul>

<ul>
 <li>Flatpak runtime update to version 5.15-23.08</li>
 <li>PyTorch update to version 2.2.1</li>
 <li>CUDA update to version 12.4.0</li>
 <li>CTranslate2 update to version 4.2.1</li>
 </ul>

Support for GPU acceleration with NVIDIA graphics cards in Speech Note

A set of libraries providing GPU acceleration with AMD graphics cards.

Speech Note AMD

<ul>
 <li>whisper.cpp update to version 1.7.1</li>
 <li>ROCm update to version 6.2.2</li>
 <li>PyTorch update to version 2.5.1</li>
 </ul>

<ul>
 <li>Flatpak runtime update to version 5.15-23.08</li>
 <li>PyTorch update to version 2.2.1</li>
 <li>ROCm update to version 5.7.3</li>
 <li>CTranslate2 update to version 4.2.1</li>
 </ul>

Support for GPU acceleration with AMD graphics cards in Speech Note

Speech Note let you take, read and translate notes in multiple languages.
 It uses Speech to Text, Text to Speech and Machine Translation to do so.
 Text and voice processing take place entirely offline, locally on your
 computer, without using a network connection. Your privacy is always
 respected. No data is sent to the Internet.

Speech Note

General:
 <ul>
 <li>Fix: The application failed to start when the processor did not support AVX CPU extension.</li>
 </ul>
 Translator:
 <ul>
 <li>New models: Korean to English, Japanese to English</li>
 <li>Updated models: Chinese to English</li>
 </ul>

General:
 <ul>
 <li>Rules for text transformations that can be applied after Speech to Text or before Text to Speech.
 With Rules, you can easily and flexibly correct errors in decoded text or correct mispronounced words.</li>
 <li>New modes for inserting text at the cursor position or replacing the current note.
 To insert text at the cursor position rather than at the end of the note,
 change 'Text appending mode' option to 'Add at the cursor position' in the settings.
 When the 'Replace an existing note' option is set, whenever new text is added, it will replace the existing note.</li>
 <li>DBus API for integration with external applications</li>
 </ul>
 User Interface:
 <ul>
 <li>Speech Note has been translated into Slovenian language.</li>
 <li>Status indication in the system tray icon.
 When using the system tray icon, statuses such as processing, listening, etc. are presented with an animated tray icon.</li>
 <li>Models grouped by type in model browser.
 To improve usability, instead of a list containing models of all types, models are grouped by type in separate tabs.</li>
 <li>Command line options for printing available or active model.</li>
 <li>Command line option to print the current status of the application.</li>
 </ul>
 Speech to Text:
 <ul>
 <li>Support for Vulkan GPU acceleration in 'WhisperCpp'.
 Vulkan acceleration enables much faster STT decoding with Intel, AMD or NVIDIA graphics cards.
 The biggest advantage of Vulkan is that you can use it without installing any GPU acceleration add-ons.</li>
 <li>New 'Whisper Large Turbo' model for both 'WhisperCpp' and 'FasterWhisper'.
 Turbo is a finetuned version of a pruned 'Whisper Large-v3'. It's the exact same model,
 except that the number of decoding layers have reduced. As a result, the model is way faster,
 at the expense of a minor quality degradation.</li>
 <li>Simplified engine configuration options. Instead of multiple options, you can now select a Profile,
 which allows you to change the engine's processing parameters.
 There are three profiles to choose from: 'Best Performance', 'Best Quality' and 'Custom'.</li>
 <li>Echo mode. After processing, the decoded text will be immediately read out using the currently set Text to Speech model.</li>
 </ul>
 Text to Speech:
 <ul>
 <li>New 'Piper' voice for Latvian</li>
 <li>New 'WhisperSpeech Small' model for: English, Italian, German, French, Spanish, Dutch and Portuguese</li>
 </ul>
 Translator:
 <ul>
 <li>New models: English to Finnish, English to Turkish, English to Swedish, Swedish to English,
 English to Slovak, English to Indonesian, English to Romanian, English to Greek, Chinese to English</li>
 <li>Updated models: English to Catalan, English to Russian, English to Ukrainian, English to Czech</li>
 </ul>
 Accessibility:
 <ul>
 <li>Option to scan special keystrokes when setting keyboard shortcuts (X11 only).
 If you want to use special keys as shortcuts (so-called multimedia keys),
 instead of typing their name, you can automatically set the key by pressing it.</li>
 <li>Keyboard shortcuts enabled for several user interface elements.
 Elements such as menu items or buttons can be controlled using the keyboard shortcuts.</li>
 <li>New 'Actions' and global keyboard shortcut to force translation of text in STT:
 'start-listening-translate', 'start-listening-translate-active-window', 'start-listening-translate-clipboard'.
 The decoded text is always translated into English when the "translate" action is triggered.
 This only works when using Whisper models.</li>
 <li>New 'Action' to read text from the command-line option: 'start-reading-text'.
 To pass text, use the '--text' option in the command-line interface.</li>
 </ul>
 Flatpak:
 <ul>
 <li>whisper.cpp update to version 1.7.1</li>
 <li>PyTorch update to version 2.5.1</li>
 <li>The Flatpak GPU acceleration add-on for AMD is no longer recommended.
 Better results can be achieved with Vulkan acceleration, which does not require the add-on.</li>
 </ul>

General:
 <ul>
 <li>Fix: The application failed to start when the processor did not support the required CPU extension.</li>
 </ul>
 User Interface:
 <ul>
 <li>Swedish translation has been updated.</li>
 </ul>
 Accessibility:
 <ul>
 <li>Fix: Special keyboard keys were not supported as a keyboard shortcut.
 Examples: 'Favorites', 'Launch Mail', 'Refresh', 'Home Page', 'Calculator' and many more...</li>
 </ul>
 Translator:
 <ul>
 <li>New models: English to Latvian, English to Danish, English to Croatian, English to Slovenian,
 Indonesian to English, Romanian to English</li>
 <li>Updated models: English to Hungarian, Czech to English, Greek to English</li>
 </ul>

User Interface:
 <ul>
 <li>Speech Note has been translated into Norwegian language.</li>
 <li>Grouped models.
 Models that provide multiple sub-models (for example, TTS models that provide different voices)
 are shown in groups. This makes it easier to find models in the model browser.</li>
 </ul>
 Speech to Text:
 <ul>
 <li>The name of the all Whisper models has been changed to 'WhisperCpp' to better reflect the engine behind them.
 Whisper is currently supported by the 'WhisperCpp' and 'FasterWhisper' engines.
 Both engines are optimized to achieve the best performance.</li>
 <li>Automatic language detection in STT.
 To automatically detect the language during STT, select one of the models that is in the 'Auto detected'
 category in the language list.</li>
 <li>Separate settings for engines.
 The configuration of each engine has been separated in the settings.
 You can separately set the parameters for 'WhisperCpp' and 'FasterWhisper'.
 The new configuration parameters that have been added to the settings are:
 'Number of simultaneous threads', 'Beam search width',
 'Audio context size', 'Use Flash Attention'.</li>
 <li>Quicker decoding with 'WhisperCpp'.
 Optimization for short sentences has been added to 'WhisperCpp' engine. With it, the speed of STT has doubled!</li>
 <li>Support for OpenVINO hardware acceleration in 'WhisperCpp.
 With OpenVINO decoding on CPU is much quicker. If you are not using GPU acceleration,
 it is recommended to enable OpenVINO in 'WhisperCpp' engine settings.
 Currently, OpenVINO is enabled only for CPU acceleration.</li>
 <li>Option for inserting processing statistics.
 New settings option allows inserting processing related information to the text after decoding,
 such as processing time and audio length. This can be useful for comparing the performance of different models,
 engines and their parameters.</li>
 </ul>
 Text to Speech:
 <ul>
 <li>Control tags for advance TTS processing.
 Control tags allow you to dynamically change the speed of synthesized text or add silence between sentences.
 To use control tags, insert '{speed: 0.5}' or '{silence: 1s}' into the text.
 For convenience, you can also insert predefined control tags using text context menu 'Insert control tag'.</li>
 <li>Welsh language. New language is enabled with 'Piper' voice.</li>
 <li>New 'Piper' voices for Spanish, Italian and English</li>
 <li>New 'RHVoice' voices for Slovak and Croatian</li>
 </ul>
 Translator:
 <ul>
 <li>Improved Translator UI.
 The 'Translate', 'Switch languages' and 'Add' buttons have been
 placed between text areas which is more convenient.</li>
 <li>Support for older hardware.
 Until now, the translator did not work on older processors without CPU AVX extension. Now there is no such restriction anymore.</li>
 <li>New models: English to Lithuanian, Croatian to English, Latvian to English, Danish to English, Serbian to English,
 Slovak to English, Bosnian to English, Vietnamese to English</li>
 <li>Updated models: Lithuanian to English, Slovenian to English, Russian to English, Ukrainian to English</li>
 </ul>
 Flatpak:
 <ul>
 <li>New library: OpenVINO version 2024.1.0.15008</li>
 <li>whisper.cpp update to version 1.6.2</li>
 <li>CTranslate2 update to version 4.3.1</li>
 </ul>

Notes with offline Speech to Text, Text to Speech and Machine Translation

Jupii let you play audio, video and image files on any device on your local network that supports UPnP/DLNA, such as smart speaker, smart TVs, gaming consoles, and more.
      In addition to the typical features you might expect from this type of application, Jupii also has some unique functionalities such as:
      
        support many different internet services as media source (Bandcamp, SoundCloud, YouTube and many more)
        live casting of video/audio from camera or microphone
        screen mirroring
        recorder that let you to extract music from Internet radio streams
      
      This app can be used in two different UPnP/DLNA modes:
      
        Playback control mode: Using Jupii, you connect to the player device (e.g. smart speaker) and transfer media from your phone/computer to this device.
        Media server mode: Using your playback device (e.g. smart TV), you browse and play media files shared by Jupii
      
    

Speech Note

Notes with offline Speech to Text, Text to Speech and Machine Translation

Changes in version 4.7.1

Community built

Other apps by Michal Kosciesza